Re: [PATCH v9 6/9] nvmet: add copy command support for bdev and file ns
From: Chaitanya Kulkarni
Date: Tue Apr 25 2023 - 02:37:04 EST
On 4/11/23 01:10, Anuj Gupta wrote:
> From: Nitesh Shetty <nj.shetty@xxxxxxxxxxx>
>
> Add support for handling target command on target.
what is target command ?
command that you have added is :nvme_cmd_copy
> For bdev-ns we call into blkdev_issue_copy, which the block layer
> completes by a offloaded copy request to backend bdev or by emulating the
> request.
>
> For file-ns we call vfs_copy_file_range to service our request.
>
> Currently target always shows copy capability by setting
> NVME_CTRL_ONCS_COPY in controller ONCS.
there is nothing mentioned about target/loop.c in commit log ?
> Signed-off-by: Nitesh Shetty <nj.shetty@xxxxxxxxxxx>
> Signed-off-by: Anuj Gupta <anuj20.g@xxxxxxxxxxx>
> ---
> drivers/nvme/target/admin-cmd.c | 9 +++--
> drivers/nvme/target/io-cmd-bdev.c | 58 +++++++++++++++++++++++++++++++
> drivers/nvme/target/io-cmd-file.c | 52 +++++++++++++++++++++++++++
> drivers/nvme/target/loop.c | 6 ++++
> drivers/nvme/target/nvmet.h | 1 +
> 5 files changed, 124 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
> index 80099df37314..978786ec6a9e 100644
> --- a/drivers/nvme/target/admin-cmd.c
> +++ b/drivers/nvme/target/admin-cmd.c
> @@ -433,8 +433,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
> id->nn = cpu_to_le32(NVMET_MAX_NAMESPACES);
> id->mnan = cpu_to_le32(NVMET_MAX_NAMESPACES);
> id->oncs = cpu_to_le16(NVME_CTRL_ONCS_DSM |
> - NVME_CTRL_ONCS_WRITE_ZEROES);
> -
> + NVME_CTRL_ONCS_WRITE_ZEROES | NVME_CTRL_ONCS_COPY);
> /* XXX: don't report vwc if the underlying device is write through */
> id->vwc = NVME_CTRL_VWC_PRESENT;
>
> @@ -536,6 +535,12 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
>
> if (req->ns->bdev)
> nvmet_bdev_set_limits(req->ns->bdev, id);
> + else {
> + id->msrc = (u8)to0based(BIO_MAX_VECS - 1);
> + id->mssrl = cpu_to_le16(BIO_MAX_VECS <<
> + (PAGE_SHIFT - SECTOR_SHIFT));
> + id->mcl = cpu_to_le32(le16_to_cpu(id->mssrl));
> + }
>
> /*
> * We just provide a single LBA format that matches what the
> diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
> index c2d6cea0236b..0af273097aa4 100644
> --- a/drivers/nvme/target/io-cmd-bdev.c
> +++ b/drivers/nvme/target/io-cmd-bdev.c
> @@ -46,6 +46,19 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
> id->npda = id->npdg;
> /* NOWS = Namespace Optimal Write Size */
> id->nows = to0based(bdev_io_opt(bdev) / bdev_logical_block_size(bdev));
> +
> + /*Copy limits*/
above comment doesn't make any sense ...
> + if (bdev_max_copy_sectors(bdev)) {
> + id->msrc = id->msrc;
> + id->mssrl = cpu_to_le16((bdev_max_copy_sectors(bdev) <<
> + SECTOR_SHIFT) / bdev_logical_block_size(bdev));
> + id->mcl = cpu_to_le32(id->mssrl);
> + } else {
> + id->msrc = (u8)to0based(BIO_MAX_VECS - 1);
> + id->mssrl = cpu_to_le16((BIO_MAX_VECS << PAGE_SHIFT) /
> + bdev_logical_block_size(bdev));
> + id->mcl = cpu_to_le32(id->mssrl);
> + }
> }
>
> void nvmet_bdev_ns_disable(struct nvmet_ns *ns)
> @@ -184,6 +197,19 @@ static void nvmet_bio_done(struct bio *bio)
> nvmet_req_bio_put(req, bio);
> }
>
> +static void nvmet_bdev_copy_end_io(void *private, int comp_len)
> +{
> + struct nvmet_req *req = (struct nvmet_req *)private;
> +
> + if (comp_len == req->copy_len) {
> + req->cqe->result.u32 = cpu_to_le32(1);
> + nvmet_req_complete(req, errno_to_nvme_status(req, 0));
> + } else {
> + req->cqe->result.u32 = cpu_to_le32(0);
> + nvmet_req_complete(req, blk_to_nvme_status(req, BLK_STS_IOERR));
> + }
> +}
> +
please reduce calls for nvmet_req_complete().
+static void nvmet_bdev_copy_end_io(void *private, int comp_len)
+{
+ struct nvmet_req *req = (struct nvmet_req *)private;
+ u16 status;
+
+ if (comp_len == req->copy_len) {
+ req->cqe->result.u32 = cpu_to_le32(1);
+ status = errno_to_nvme_status(req, 0));
+ } else {
+ req->cqe->result.u32 = cpu_to_le32(0);
+ status = blk_to_nvme_status(req, BLK_STS_IOERR));
+ }
+ nvmet_req_complete(req, status);
+}
+
> #ifdef CONFIG_BLK_DEV_INTEGRITY
> static int nvmet_bdev_alloc_bip(struct nvmet_req *req, struct bio *bio,
> struct sg_mapping_iter *miter)
> @@ -450,6 +476,34 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req)
> }
> }
>
> +/* At present we handle only one range entry */
please add explanation why ...
> +static void nvmet_bdev_execute_copy(struct nvmet_req *req)
> +{
> + struct nvme_copy_range range;
> + struct nvme_command *cmnd = req->cmd;
don't use cmnd, cmd is used everywhere and matches req->cmd,
applies to everywhere in this patch...
> + int ret;
wrong return type is should be u16 since nvmet_copy_from_sgl()
returns u16 if I remember correctly.
> +
> +
no extra white line between declaration and body of functions
> + ret = nvmet_copy_from_sgl(req, 0, &range, sizeof(range));
> + if (ret)
> + goto out;
> +
> + ret = blkdev_issue_copy(req->ns->bdev,
> + le64_to_cpu(cmnd->copy.sdlba) << req->ns->blksize_shift,
> + req->ns->bdev,
> + le64_to_cpu(range.slba) << req->ns->blksize_shift,
> + (le16_to_cpu(range.nlb) + 1) << req->ns->blksize_shift,
> + nvmet_bdev_copy_end_io, (void *)req, GFP_KERNEL);
> + if (ret) {
> + req->cqe->result.u32 = cpu_to_le32(0);
> + nvmet_req_complete(req, blk_to_nvme_status(req, BLK_STS_IOERR));
> + }
> +
> + return;
> +out:
> + nvmet_req_complete(req, errno_to_nvme_status(req, ret));
> +}
> +
again one call to nvmet_req_complete() can do the same job.
consider following totally untested :-
/* TODO: add detailed comment here why you support one range ? */
static void nvmet_bdev_execute_copy(struct nvmet_req *req)
{
u32 blkshift = req->ns->blksize_shift;
struct nvme_command *cmnd = req->cmd;
struct nvme_copy_range range;
u16 status;
status = nvmet_copy_from_sgl(req, 0, &range, sizeof(range));
if (status) {
goto out;
}
ret = blkdev_issue_copy(req->ns->bdev,
le64_to_cpu(cmnd->copy.sdlba) << blkshift,
req->ns->bdev,
le64_to_cpu(range.slba) << blksize_shift,
(le16_to_cpu(range.nlb) + 1) <<
blksize_shift,
nvmet_bdev_copy_end_io, (void *)req,
GFP_KERNEL);
if (ret) {
req->cqe->result.u32 = cpu_to_le32(0);
status = blk_to_nvme_status(req, BLK_STS_IOERR);
out:
nvmet_req_complete(req, status);
}
}
> u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req)
> {
> switch (req->cmd->common.opcode) {
> @@ -468,6 +522,10 @@ u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req)
> case nvme_cmd_write_zeroes:
> req->execute = nvmet_bdev_execute_write_zeroes;
> return 0;
> + case nvme_cmd_copy:
> + req->execute = nvmet_bdev_execute_copy;
> + return 0;
> +
> default:
> return nvmet_report_invalid_opcode(req);
> }
> diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
> index 2d068439b129..69f198ecec77 100644
> --- a/drivers/nvme/target/io-cmd-file.c
> +++ b/drivers/nvme/target/io-cmd-file.c
> @@ -322,6 +322,49 @@ static void nvmet_file_dsm_work(struct work_struct *w)
> }
> }
>
> +static void nvmet_file_copy_work(struct work_struct *w)
> +{
> + struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
> + int nr_range;
> + loff_t pos;
> + struct nvme_command *cmnd = req->cmd;
> + int ret = 0, len = 0, src, id;
reverse tree style for declaration ...
> +
> + nr_range = cmnd->copy.nr_range + 1;
> + pos = le64_to_cpu(req->cmd->copy.sdlba) << req->ns->blksize_shift;
you have a cmd variable above and you are still using req->cmd ?
why create a variable on stack then ? u don't need that variable
anyways...
> + if (unlikely(pos + req->transfer_len > req->ns->size)) {
> + nvmet_req_complete(req, errno_to_nvme_status(req, -ENOSPC));
> + return;
> + }
> +
> + for (id = 0 ; id < nr_range; id++) {
> + struct nvme_copy_range range;
> +
> + ret = nvmet_copy_from_sgl(req, id * sizeof(range), &range,
> + sizeof(range));
> + if (ret)
> + goto out;
> +
> + len = (le16_to_cpu(range.nlb) + 1) << (req->ns->blksize_shift);
> + src = (le64_to_cpu(range.slba) << (req->ns->blksize_shift));
> + ret = vfs_copy_file_range(req->ns->file, src, req->ns->file,
> + pos, len, 0);
5th paramaeter to vfs_copy_file_range() is size_t you have used int
for len ? also
vfs_copy_file_range() returns ssize_t you are catching it in int ?
> +out:
> + if (ret != len) {
> + pos += ret;
> + req->cqe->result.u32 = cpu_to_le32(id);
> + nvmet_req_complete(req, ret < 0 ?
> + errno_to_nvme_status(req, ret) :
> + errno_to_nvme_status(req, -EIO));
again plz don't add multiple nvmet_req_complete() calls
> + return;
> +
> + } else
> + pos += len;
> + }
> +
> + nvmet_req_complete(req, 0);
> +
> +}
wrt above comments consider following totally untested :-
static void nvmet_file_copy_work(struct work_struct *w)
{
struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
int nr_range = req->cmd->copy.nr_range + 1;
u16 status = 0;
int src, id;
ssize_t ret;
size_t len;
loff_t pos;
pos = le64_to_cpu(req->cmd->copy.sdlba) << req->ns->blksize_shift;
if (unlikely(pos + req->transfer_len > req->ns->size)) {
nvmet_req_complete(req, errno_to_nvme_status(req,
-ENOSPC));
return;
}
for (id = 0 ; id < nr_range; id++) {
struct nvme_copy_range range;
status = nvmet_copy_from_sgl(req, id * sizeof(range),
&range,
sizeof(range));
if (status)
goto out;
src = (le64_to_cpu(range.slba) <<
(req->ns->blksize_shift));
len = (le16_to_cpu(range.nlb) + 1) <<
(req->ns->blksize_shift);
ret = vfs_copy_file_range(req->ns->file, src,
req->ns->file,
pos, len, 0);
if (ret != len) {
req->cqe->result.u32 = cpu_to_le32(id);
if (ret < 0)
status = errno_to_nvme_status(req, ret);
else
status = errno_to_nvme_status(req, -EIO);
goto out;
}
pos += ret;
}
out:
nvmet_req_complete(req, status);
}
> static void nvmet_file_execute_dsm(struct nvmet_req *req)
> {
> if (!nvmet_check_data_len_lte(req, nvmet_dsm_len(req)))
> @@ -330,6 +373,12 @@ static void nvmet_file_execute_dsm(struct nvmet_req *req)
> queue_work(nvmet_wq, &req->f.work);
> }
>
> +static void nvmet_file_execute_copy(struct nvmet_req *req)
> +{
> + INIT_WORK(&req->f.work, nvmet_file_copy_work);
> + queue_work(nvmet_wq, &req->f.work);
> +}
> +
> static void nvmet_file_write_zeroes_work(struct work_struct *w)
> {
> struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
> @@ -376,6 +425,9 @@ u16 nvmet_file_parse_io_cmd(struct nvmet_req *req)
> case nvme_cmd_write_zeroes:
> req->execute = nvmet_file_execute_write_zeroes;
> return 0;
> + case nvme_cmd_copy:
> + req->execute = nvmet_file_execute_copy;
> + return 0;
> default:
> return nvmet_report_invalid_opcode(req);
> }
> diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
> index f2d24b2d992f..d18ed8067a15 100644
> --- a/drivers/nvme/target/loop.c
> +++ b/drivers/nvme/target/loop.c
> @@ -146,6 +146,12 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
> return ret;
>
> nvme_start_request(req);
> + if (unlikely((req->cmd_flags & REQ_COPY) &&
> + (req_op(req) == REQ_OP_READ))) {
> + blk_mq_set_request_complete(req);
> + blk_mq_end_request(req, BLK_STS_OK);
> + return BLK_STS_OK;
> + }
> iod->cmd.common.flags |= NVME_CMD_SGL_METABUF;
> iod->req.port = queue->ctrl->port;
> if (!nvmet_req_init(&iod->req, &queue->nvme_cq,
> diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
> index 89bedfcd974c..69ed4c8469e5 100644
> --- a/drivers/nvme/target/nvmet.h
> +++ b/drivers/nvme/target/nvmet.h
> @@ -393,6 +393,7 @@ struct nvmet_req {
> struct device *p2p_client;
> u16 error_loc;
> u64 error_slba;
> + size_t copy_len;
> };
>
> #define NVMET_MAX_MPOOL_BVEC 16
-ck